Upload folder using huggingface_hub
Browse files- README.md +13 -11
- merges.txt +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,8 +1,10 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
language:
|
| 4 |
-
-
|
| 5 |
-
-
|
|
|
|
|
|
|
| 6 |
tags:
|
| 7 |
- tokenizer
|
| 8 |
- bpe
|
|
@@ -10,31 +12,31 @@ tags:
|
|
| 10 |
- fineweb2
|
| 11 |
---
|
| 12 |
|
| 13 |
-
# Byte-Level BPE Tokenizer: ['
|
| 14 |
|
| 15 |
-
A **Byte-Level BPE** tokenizer trained on **['
|
| 16 |
|
| 17 |
## Training Details
|
| 18 |
|
| 19 |
| Parameter | Value |
|
| 20 |
|-----------|-------|
|
| 21 |
| Algorithm | Byte-Level BPE |
|
| 22 |
-
| Language | `['
|
| 23 |
-
| Target Vocab Size |
|
| 24 |
-
| Final Vocab Size |
|
| 25 |
-
| Pre-tokenizer | custom:
|
| 26 |
| Number handling | ltr_3digit |
|
| 27 |
| Contraction handling | True |
|
| 28 |
| Normalizer | NFC |
|
| 29 |
| Special Tokens | `<s>`, `</s>`, `<pad>`, `<unk>` |
|
| 30 |
-
| Training Shards |
|
| 31 |
|
| 32 |
## Usage
|
| 33 |
|
| 34 |
```python
|
| 35 |
from transformers import AutoTokenizer
|
| 36 |
|
| 37 |
-
tokenizer = AutoTokenizer.from_pretrained("flexitok/
|
| 38 |
tokens = tokenizer.encode("Hello, world!")
|
| 39 |
```
|
| 40 |
|
|
@@ -47,4 +49,4 @@ tokens = tokenizer.encode("Hello, world!")
|
|
| 47 |
## Sample Encoding
|
| 48 |
| Text | Tokens | Token IDs |
|
| 49 |
|------|--------|-----------|
|
| 50 |
-
| `Hello, world! 12345 This is a test. こんにちは` | `H,
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
language:
|
| 4 |
+
- dan
|
| 5 |
+
- deu
|
| 6 |
+
- nld
|
| 7 |
+
- swe #['dan_Latn', 'deu_Latn', 'nld_Latn', 'swe_Latn'] # ISO 639-3 code or "und" if not identifiable
|
| 8 |
tags:
|
| 9 |
- tokenizer
|
| 10 |
- bpe
|
|
|
|
| 12 |
- fineweb2
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# Byte-Level BPE Tokenizer: ['dan_Latn', 'deu_Latn', 'nld_Latn', 'swe_Latn'] (32K)
|
| 16 |
|
| 17 |
+
A **Byte-Level BPE** tokenizer trained on **['dan_Latn', 'deu_Latn', 'nld_Latn', 'swe_Latn']** data from Fineweb-2-HQ.
|
| 18 |
|
| 19 |
## Training Details
|
| 20 |
|
| 21 |
| Parameter | Value |
|
| 22 |
|-----------|-------|
|
| 23 |
| Algorithm | Byte-Level BPE |
|
| 24 |
+
| Language | `['dan_Latn', 'deu_Latn', 'nld_Latn', 'swe_Latn']` |
|
| 25 |
+
| Target Vocab Size | 32,000 |
|
| 26 |
+
| Final Vocab Size | 32,865 |
|
| 27 |
+
| Pre-tokenizer | custom:dan_Latn |
|
| 28 |
| Number handling | ltr_3digit |
|
| 29 |
| Contraction handling | True |
|
| 30 |
| Normalizer | NFC |
|
| 31 |
| Special Tokens | `<s>`, `</s>`, `<pad>`, `<unk>` |
|
| 32 |
+
| Training Shards | 8 |
|
| 33 |
|
| 34 |
## Usage
|
| 35 |
|
| 36 |
```python
|
| 37 |
from transformers import AutoTokenizer
|
| 38 |
|
| 39 |
+
tokenizer = AutoTokenizer.from_pretrained("flexitok/bpe_script_Germ_32000")
|
| 40 |
tokens = tokenizer.encode("Hello, world!")
|
| 41 |
```
|
| 42 |
|
|
|
|
| 49 |
## Sample Encoding
|
| 50 |
| Text | Tokens | Token IDs |
|
| 51 |
|------|--------|-----------|
|
| 52 |
+
| `Hello, world! 12345 This is a test. こんにちは` | `H, ello, ,, Ġworld, !, Ġ, 123, 45, ĠThis, Ġis, Ġa, Ġtest, ., Ġ, ãģ, ĵ, ãĤ, ĵ, ãģ«, ãģ` | `42, 13486, 14, 21745, 3, 223, 19219, 3832, 16775, 516, 270, 5190, 16, 223, 3768, 244, 5986, 244, 30698, 3768` |
|
merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|